Update README.md

README.md

@@ -1,20 +1,22 @@
 ---
 library_name: keras
+license: mit
+language:
+- ar
 ---
 
 ## Model description
 
-More information needed
-
-## Intended uses & limitations
-
-More information needed
+This  2dCNNmsda model is a two-dimensional convolutional neural network  (2D-CNN) architecture trained from scratch on Sentiment Analysis for Social Media Posts in Arabic Dialect (MSDA) dataset with three window sizes of 3, 4, and 5, and 100 filters for each window size.
+It achieves the following results on the evaluation test set:
+Accuracy: 77%
 
 ## Training and evaluation data
 
-More information needed
+We trained this model on a 90% train set and evaluated it on a 10% test set.
 
 ## Training procedure
+We have trained this model using the Paperspace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
 
 ### Training hyperparameters
 
@@ -23,13 +25,9 @@ The following hyperparameters were used during training:
 | Hyperparameters | Value |
 | :-- | :-- |
 | name | Adam |
-| learning_rate | 0.0010000000474974513 |
-| decay | 0.0 |
-| beta_1 | 0.8999999761581421 |
-| beta_2 | 0.9990000128746033 |
-| epsilon | 1e-07 |
-| amsgrad | False |
-| training_precision | float32 |
+train_batch_size: 128   
+num_epochs: 15
+
 
 
  ## Model Plot